6 papers
Event-triggered Implicit Perturbation for Zeroth-Order Fine-Tuning of Spiking Transformers
Tengteng Lei, Prabodh Katti, Rashi Dutt +5
Zeroth-order (ZO) optimization estimates gradients using only forward-pass evaluations, making it suitable for fine-tuning non-differentiable, event-driven spiking neural networks…
Efficient transformer adaptation for analog in-memory computing via low-rank adapters
Chen Li, Elena Ferro, Corey Lammie +3
Analog In-Memory Computing (AIMC) offers a promising solution to the von Neumann bottleneck. However, deploying transformer models on AIMC remains challenging due to their inherent…
Closed-Form Feedback-Free Learning with Forward Projection
Robert O'Shea, Bipin Rajendran
State-of-the-art backpropagation-free learning methods employ local error feedback to direct iterative optimisation via gradient descent. Here, we examine the more restrictive sett…
Xpikeformer: Hybrid Analog-Digital Hardware Acceleration for Spiking Transformers
Zihang Song, Prabodh Katti, Osvaldo Simeone +1
The integration of neuromorphic computing and transformers through spiking neural networks (SNNs) offers a promising path to energy-efficient sequence modeling, with the potential…
Bayes2IMC: In-Memory Computing for Bayesian Binary Neural Networks
Prabodh Katti, Clement Ruah, Osvaldo Simeone +2
Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-inten…
Noise Adaptor: Enhancing Low-Latency Spiking Neural Networks through Noise-Injected Low-Bit ANN Conversion
Chen Li, Bipin. Rajendran
We present Noise Adaptor, a novel method for constructing competitive low-latency spiking neural networks (SNNs) by converting noise-injected, low-bit artificial neural networks (A…